A new approach for iris localization in iris recognition systems

Abstract

This paper presents a new approach for iris localization which consists of one of the most important steps in an iris recognition system. We have solved some of the most important drawbacks of the current methods using a pointwise level set algorithm, which detects the precise location of the iris by a stepwise deformation of an initial contour. Due to the special properties of our approach, there is no constraint about angles of head tilt. Furthermore, this algorithm is robust in noisy situations and can find irises which are partly occluded by eyelid and eyelashes. This is done by using a topology preserving technique in only one step to find both inner and outer boundaries. Another advantage of our method is its ability to find iris in images which include other parts of face. This pointwise level set approach makes it possible to perform the operations of the iris localization and mapping of iris coordinates to a polar dimension simultaneously, an approach which decreases the processing time of the system considerably. The experimental results show that the proposed method outperforms the current methods both in terms of accuracy and response time.

An efficient iris segmentation approach

“…This method demonstrated faster feature extraction process, but still have extra cost during feature reduction using MOGA and suitable for small dataset like ICE. Barzegar et al [17] proposed a method to detect the exact location of iris boundaries regardless of head tilt, or existence of other part of faces and existence of noise in the input image. Richard et al [18] discussed the effect of noises such as eyelids, eyelashes, reflection and pupil noises on iris segmentation and proposed an approach to give a solution for compensating all four types of noises to achieve higher accuracy rate, but the dataset used here not enough to test this approach.…”

Comparison of Color and Texture for Iris Recognition

“…It turns out, rather remarkably, that if we choose scales and positions based on powers of two, which is called dyadic scales and positions then our analysis will be much more e±cient and accurate. We obtain such an analysis from the DWT given by (2).…”

“…There are number of algorithms for iris recognition. To mention a few very recent ones are Ali et al,1 Barzegar and Moin,2 Bashir et al,3,4 Boddeti et al,10 and Ali et al, 2À6,10 All these methods are based on iris normalization. Lu and Xie 30 used fractional calculus for iris localization.…”

Iris Recognition Using Ridgelets

“…Irises as a biometric for identification have been an active research area since 1992. The uniqueness of iris patterns was identified by A. Muron and J. Pospisil, [1][2][3][4][5]. This uniqueness property of irises can be explained in the words of Daugman [6,7] as, "An advantage that the iris shares with finger prints is the chaotic morphogenesis of its minutiae."…”

“…Figs. 3(2) and 3 (3) show that eyelid and eyelash occlusions can be avoided by the use of a proper mask for segmentation. The use of an appropriate mask avoids unnecessary processing.…”